© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 507
    Prev
    Next
    INDEX
    Explanations

    names after '

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ka
    -0.21
    k
    -0.17
    ta
    -0.16
    na
    -0.16
    b
    -0.15
    la
    -0.15
    sa
    -0.14
    d
    -0.14
    l
    -0.14
    v
    -0.14
    POSITIVE LOGITS
    ught
    0.16
    Ñħ
    0.15
    frica
    0.15
    eus
    0.15
    eb
    0.14
    forge
    0.14
    ÑİÑĤ
    0.14
    udio
    0.14
    resh
    0.13
    ÑİÑī
    0.13
    Activations Density 1.810%

    No Known Activations